AI-Assisted Breast Cancer Classification: A Deep Learning Model Integrating MobileNet and ShuffleNet Features

Early detection of breast cancer is essential for enhancing treatment effectiveness and lowering mortality rates. Manual analysis of histopathological images results in delayed diagnoses because it relies heavily on the expertise of trained pathologists. In this study, we present a novel deep-learning-based method for classifying breast cancer subtypes in microscopic images of stained cellular structures. Our approach utilizes the power of convolutional neural networks with skip connections and transfer learning. The technique uses the computational efficiency of MobileNet and ShuffleNet to extract complex features and yield highly accurate diagnostic insights. The proposed model excels at identifying intricate cellular patterns that may indicate cancer progression, achieving superior performance metrics, including accuracy, precision, recall, and an F1-score exceeding 99% on the BreakHis dataset. Comprehensive evaluations against current approaches demonstrate the strength and consistency of the proposed method in accurately identifying breast cancer subtypes.